Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

added_tokens.json

@@ -0,0 +1,28 @@
+{
+  "</think>": 151668,
+  "</tool_call>": 151658,
+  "</tool_response>": 151666,
+  "<think>": 151667,
+  "<tool_call>": 151657,
+  "<tool_response>": 151665,
+  "<|box_end|>": 151649,
+  "<|box_start|>": 151648,
+  "<|endoftext|>": 151643,
+  "<|file_sep|>": 151664,
+  "<|fim_middle|>": 151660,
+  "<|fim_pad|>": 151662,
+  "<|fim_prefix|>": 151659,
+  "<|fim_suffix|>": 151661,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644,
+  "<|image_pad|>": 151655,
+  "<|object_ref_end|>": 151647,
+  "<|object_ref_start|>": 151646,
+  "<|quad_end|>": 151651,
+  "<|quad_start|>": 151650,
+  "<|repo_name|>": 151663,
+  "<|video_pad|>": 151656,
+  "<|vision_end|>": 151653,
+  "<|vision_pad|>": 151654,
+  "<|vision_start|>": 151652
+}

config.json

@@ -0,0 +1,38 @@
+{
+  "architectures": [
+    "Qwen3MoeForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "decoder_sparse_step": 1,
+  "eos_token_id": 151643,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 2048,
+  "initializer_range": 0.02,
+  "intermediate_size": 6144,
+  "max_position_embeddings": 32768,
+  "max_window_layers": 48,
+  "mlp_only_layers": [],
+  "model_type": "qwen3_moe",
+  "moe_intermediate_size": 768,
+  "norm_topk_prob": true,
+  "num_attention_heads": 32,
+  "num_experts": 128,
+  "num_experts_per_tok": 8,
+  "num_hidden_layers": 48,
+  "num_key_value_heads": 4,
+  "output_router_logits": false,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000000.0,
+  "router_aux_loss_coef": 0.001,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.51.3",
+  "use_cache": false,
+  "use_sliding_window": false,
+  "vocab_size": 151936
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "bos_token_id": 151643,
+  "eos_token_id": 151643,
+  "max_new_tokens": 2048,
+  "transformers_version": "4.51.3"
+}

model-00001-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:19bee42fe3138e7937a8a732cb07ecf6618c571587fd2220205a3320770007a4
+size 4997184968

model-00002-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ada4ac31bde8304b684824f5733343cf389a498b7fc90b5cc6b773a0130a32fc
+size 4997741608

model-00003-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:374474d5a7ce786d93b7cc4195b7bbc974114a835adc8b6e739ef92b4a50f121
+size 4997742208

model-00004-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4641ed3a29b9e4b6eac588563992cf41c6585bb3f1a62bf8cc7ca9f6d1b796a1
+size 4997743184

model-00005-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9026bb1bb30e190a32cd0989a6e0f029245403e028e135e8c4a37a0345b11747
+size 4997743184

model-00006-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fb580db9a25701b49c573d1074658d9bbb6258fed7680f877b55dc529df8c72a
+size 4997743184

model-00007-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8169ca468ab32a8a66af761ec34ab6ada82aa919fed7ec0870f6d0cab1d7c35b
+size 4997743184

model-00008-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b9f63f724501e3940767acb8924406e79ecb86d0843ef8fd622c50f9f9ac2c84
+size 4997743184

model-00009-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ac04b676fbb712ec7fd37d8726ded15916cbda0628961aef03203e81a29287c4
+size 4997743184

model-00010-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0c706d5a6997aed23841af7684bbb35f078b09581b80272d99dba0854e9ceec8
+size 4997743184

model-00011-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f54893cc8b4ec76a640ac0d8ee588f1bb4af1abb8e3b68a3ecdf6e8034e87925
+size 4997743184

model-00012-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:23cb771757e5b1c38cc4f90a138ab977da987f779a2b574617c3c3e1b69c6de7
+size 4997743184

model-00013-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1f854822c9c47ae22a2761f2b1fb25e984dc15ce0218f6b9f4b6961c240a84b0
+size 1094220288

special_tokens_map.json

@@ -0,0 +1,31 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aeb13307a71acd8fe81861d94ad54ab689df773318809eed3cbe794b4492dae4
+size 11422654

tokenizer_config.json

@@ -0,0 +1,241 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151646": {
+      "content": "<|object_ref_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|object_ref_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151648": {
+      "content": "<|box_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151649": {
+      "content": "<|box_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151650": {
+      "content": "<|quad_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<|quad_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<|vision_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|vision_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<|vision_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<|image_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|video_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151657": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151658": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151659": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151660": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151661": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151662": {
+      "content": "<|fim_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151663": {
+      "content": "<|repo_name|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151664": {
+      "content": "<|file_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151665": {
+      "content": "<tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151666": {
+      "content": "</tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151667": {
+      "content": "<think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151668": {
+      "content": "</think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "bos_token": null,
+  "chat_template": "{%- if tools %}\n    {{- '<|im_start|>system\\n' }}\n    {%- if messages[0].role == 'system' %}\n        {{- messages[0].content + '\\n\\n' }}\n    {%- endif %}\n    {{- \"# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within <tools></tools> XML tags:\\n<tools>\" }}\n    {%- for tool in tools %}\n        {{- \"\\n\" }}\n        {{- tool | tojson }}\n    {%- endfor %}\n    {{- \"\\n</tools>\\n\\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\\n<tool_call>\\n{\\\"name\\\": <function-name>, \\\"arguments\\\": <args-json-object>}\\n</tool_call><|im_end|>\\n\" }}\n{%- else %}\n    {%- if messages[0].role == 'system' %}\n        {{- '<|im_start|>system\\n' + messages[0].content + '<|im_end|>\\n' }}\n    {%- endif %}\n{%- endif %}\n{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}\n{%- for message in messages[::-1] %}\n    {%- set index = (messages|length - 1) - loop.index0 %}\n    {%- if ns.multi_step_tool and message.role == \"user\" and not(message.content.startswith('<tool_response>') and message.content.endswith('</tool_response>')) %}\n        {%- set ns.multi_step_tool = false %}\n        {%- set ns.last_query_index = index %}\n    {%- endif %}\n{%- endfor %}\n{%- for message in messages %}\n    {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) %}\n        {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n    {%- elif message.role == \"assistant\" %}\n        {%- set content = message.content %}\n        {%- set reasoning_content = '' %}\n        {%- if message.reasoning_content is defined and message.reasoning_content is not none %}\n            {%- set reasoning_content = message.reasoning_content %}\n        {%- else %}\n            {%- if '</think>' in message.content %}\n                {%- set content = message.content.split('</think>')[-1].lstrip('\\n') %}\n                {%- set reasoning_content = message.content.split('</think>')[0].rstrip('\\n').split('<think>')[-1].lstrip('\\n') %}\n            {%- endif %}\n        {%- endif %}\n        {%- if loop.index0 > ns.last_query_index %}\n            {%- if loop.last or (not loop.last and reasoning_content) %}\n                {{- '<|im_start|>' + message.role + '\\n<think>\\n' + reasoning_content.strip('\\n') + '\\n</think>\\n\\n' + content.lstrip('\\n') }}\n            {%- else %}\n                {{- '<|im_start|>' + message.role + '\\n' + content }}\n            {%- endif %}\n        {%- else %}\n            {{- '<|im_start|>' + message.role + '\\n' + content }}\n        {%- endif %}\n        {%- if message.tool_calls %}\n            {%- for tool_call in message.tool_calls %}\n                {%- if (loop.first and content) or (not loop.first) %}\n                    {{- '\\n' }}\n                {%- endif %}\n                {%- if tool_call.function %}\n                    {%- set tool_call = tool_call.function %}\n                {%- endif %}\n                {{- '<tool_call>\\n{\"name\": \"' }}\n                {{- tool_call.name }}\n                {{- '\", \"arguments\": ' }}\n                {%- if tool_call.arguments is string %}\n                    {{- tool_call.arguments }}\n                {%- else %}\n                    {{- tool_call.arguments | tojson }}\n                {%- endif %}\n                {{- '}\\n</tool_call>' }}\n            {%- endfor %}\n        {%- endif %}\n        {{- '<|im_end|>\\n' }}\n    {%- elif message.role == \"tool\" %}\n        {%- if loop.first or (messages[loop.index0 - 1].role != \"tool\") %}\n            {{- '<|im_start|>user' }}\n        {%- endif %}\n        {{- '\\n<tool_response>\\n' }}\n        {{- message.content }}\n        {{- '\\n</tool_response>' }}\n        {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n            {{- '<|im_end|>\\n' }}\n        {%- endif %}\n    {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n    {{- '<|im_start|>assistant\\n' }}\n    {%- if enable_thinking is defined and enable_thinking is false %}\n        {{- '<think>\\n\\n</think>\\n\\n' }}\n    {%- endif %}\n{%- endif %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

trainer_state.json

@@ -0,0 +1,1434 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.3656307129798903,
+  "eval_steps": 500,
+  "global_step": 200,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0018281535648994515,
+      "grad_norm": 2.089374507496642,
+      "learning_rate": 0.0,
+      "loss": 0.5957,
+      "step": 1
+    },
+    {
+      "epoch": 0.003656307129798903,
+      "grad_norm": 2.2205513668741044,
+      "learning_rate": 1.0714285714285714e-06,
+      "loss": 0.5994,
+      "step": 2
+    },
+    {
+      "epoch": 0.005484460694698354,
+      "grad_norm": 2.545945852200423,
+      "learning_rate": 2.1428571428571427e-06,
+      "loss": 0.5948,
+      "step": 3
+    },
+    {
+      "epoch": 0.007312614259597806,
+      "grad_norm": 2.2330035148383947,
+      "learning_rate": 3.2142857142857143e-06,
+      "loss": 0.6305,
+      "step": 4
+    },
+    {
+      "epoch": 0.009140767824497258,
+      "grad_norm": 1.8952582634630641,
+      "learning_rate": 4.2857142857142855e-06,
+      "loss": 0.5998,
+      "step": 5
+    },
+    {
+      "epoch": 0.010968921389396709,
+      "grad_norm": 1.570960207475644,
+      "learning_rate": 5.357142857142857e-06,
+      "loss": 0.5898,
+      "step": 6
+    },
+    {
+      "epoch": 0.012797074954296161,
+      "grad_norm": 1.2522662311648174,
+      "learning_rate": 6.428571428571429e-06,
+      "loss": 0.6013,
+      "step": 7
+    },
+    {
+      "epoch": 0.014625228519195612,
+      "grad_norm": 1.065080174164971,
+      "learning_rate": 7.5e-06,
+      "loss": 0.5682,
+      "step": 8
+    },
+    {
+      "epoch": 0.016453382084095063,
+      "grad_norm": 0.9448479764184926,
+      "learning_rate": 8.571428571428571e-06,
+      "loss": 0.5452,
+      "step": 9
+    },
+    {
+      "epoch": 0.018281535648994516,
+      "grad_norm": 1.7141233153619826,
+      "learning_rate": 9.642857142857144e-06,
+      "loss": 0.59,
+      "step": 10
+    },
+    {
+      "epoch": 0.02010968921389397,
+      "grad_norm": 2.017633207813829,
+      "learning_rate": 1.0714285714285714e-05,
+      "loss": 0.575,
+      "step": 11
+    },
+    {
+      "epoch": 0.021937842778793418,
+      "grad_norm": 1.8293000392166587,
+      "learning_rate": 1.1785714285714286e-05,
+      "loss": 0.5598,
+      "step": 12
+    },
+    {
+      "epoch": 0.02376599634369287,
+      "grad_norm": 1.4816869854216612,
+      "learning_rate": 1.2857142857142857e-05,
+      "loss": 0.5495,
+      "step": 13
+    },
+    {
+      "epoch": 0.025594149908592323,
+      "grad_norm": 1.5033597863132906,
+      "learning_rate": 1.3928571428571429e-05,
+      "loss": 0.5372,
+      "step": 14
+    },
+    {
+      "epoch": 0.027422303473491772,
+      "grad_norm": 1.3141514496532496,
+      "learning_rate": 1.5e-05,
+      "loss": 0.5733,
+      "step": 15
+    },
+    {
+      "epoch": 0.029250457038391225,
+      "grad_norm": 2.7794219916654233,
+      "learning_rate": 1.6071428571428572e-05,
+      "loss": 0.5347,
+      "step": 16
+    },
+    {
+      "epoch": 0.031078610603290677,
+      "grad_norm": 0.9928713947921902,
+      "learning_rate": 1.7142857142857142e-05,
+      "loss": 0.4908,
+      "step": 17
+    },
+    {
+      "epoch": 0.03290676416819013,
+      "grad_norm": 0.8852252619423812,
+      "learning_rate": 1.8214285714285712e-05,
+      "loss": 0.5307,
+      "step": 18
+    },
+    {
+      "epoch": 0.03473491773308958,
+      "grad_norm": 0.7832318403464806,
+      "learning_rate": 1.928571428571429e-05,
+      "loss": 0.5025,
+      "step": 19
+    },
+    {
+      "epoch": 0.03656307129798903,
+      "grad_norm": 0.9796265282565124,
+      "learning_rate": 2.0357142857142858e-05,
+      "loss": 0.5095,
+      "step": 20
+    },
+    {
+      "epoch": 0.038391224862888484,
+      "grad_norm": 0.7218139820603727,
+      "learning_rate": 2.1428571428571428e-05,
+      "loss": 0.4834,
+      "step": 21
+    },
+    {
+      "epoch": 0.04021937842778794,
+      "grad_norm": 0.6506357909260763,
+      "learning_rate": 2.25e-05,
+      "loss": 0.4947,
+      "step": 22
+    },
+    {
+      "epoch": 0.04204753199268738,
+      "grad_norm": 0.5616806424289195,
+      "learning_rate": 2.357142857142857e-05,
+      "loss": 0.4866,
+      "step": 23
+    },
+    {
+      "epoch": 0.043875685557586835,
+      "grad_norm": 0.566744323961197,
+      "learning_rate": 2.464285714285714e-05,
+      "loss": 0.515,
+      "step": 24
+    },
+    {
+      "epoch": 0.04570383912248629,
+      "grad_norm": 0.6913117297678986,
+      "learning_rate": 2.5714285714285714e-05,
+      "loss": 0.5227,
+      "step": 25
+    },
+    {
+      "epoch": 0.04753199268738574,
+      "grad_norm": 0.5881117480751623,
+      "learning_rate": 2.6785714285714288e-05,
+      "loss": 0.478,
+      "step": 26
+    },
+    {
+      "epoch": 0.04936014625228519,
+      "grad_norm": 0.5399101198373484,
+      "learning_rate": 2.7857142857142858e-05,
+      "loss": 0.5039,
+      "step": 27
+    },
+    {
+      "epoch": 0.051188299817184646,
+      "grad_norm": 0.5359845255880198,
+      "learning_rate": 2.892857142857143e-05,
+      "loss": 0.5015,
+      "step": 28
+    },
+    {
+      "epoch": 0.05301645338208409,
+      "grad_norm": 0.4718417677524385,
+      "learning_rate": 3e-05,
+      "loss": 0.4738,
+      "step": 29
+    },
+    {
+      "epoch": 0.054844606946983544,
+      "grad_norm": 0.47359316021290165,
+      "learning_rate": 2.999972519478696e-05,
+      "loss": 0.4993,
+      "step": 30
+    },
+    {
+      "epoch": 0.056672760511883,
+      "grad_norm": 0.4922109148988566,
+      "learning_rate": 2.99989007892169e-05,
+      "loss": 0.4888,
+      "step": 31
+    },
+    {
+      "epoch": 0.05850091407678245,
+      "grad_norm": 0.3579397510509835,
+      "learning_rate": 2.9997526813496602e-05,
+      "loss": 0.4792,
+      "step": 32
+    },
+    {
+      "epoch": 0.0603290676416819,
+      "grad_norm": 0.37626393648031903,
+      "learning_rate": 2.9995603317969497e-05,
+      "loss": 0.4873,
+      "step": 33
+    },
+    {
+      "epoch": 0.062157221206581355,
+      "grad_norm": 0.41211122381414894,
+      "learning_rate": 2.99931303731138e-05,
+      "loss": 0.4939,
+      "step": 34
+    },
+    {
+      "epoch": 0.06398537477148081,
+      "grad_norm": 0.3770284364229165,
+      "learning_rate": 2.9990108069539932e-05,
+      "loss": 0.479,
+      "step": 35
+    },
+    {
+      "epoch": 0.06581352833638025,
+      "grad_norm": 0.3709162789872314,
+      "learning_rate": 2.9986536517987187e-05,
+      "loss": 0.4864,
+      "step": 36
+    },
+    {
+      "epoch": 0.06764168190127971,
+      "grad_norm": 0.36989388190185846,
+      "learning_rate": 2.998241584931971e-05,
+      "loss": 0.4727,
+      "step": 37
+    },
+    {
+      "epoch": 0.06946983546617916,
+      "grad_norm": 0.36339103914080506,
+      "learning_rate": 2.9977746214521646e-05,
+      "loss": 0.472,
+      "step": 38
+    },
+    {
+      "epoch": 0.0712979890310786,
+      "grad_norm": 0.3378220732996809,
+      "learning_rate": 2.997252778469168e-05,
+      "loss": 0.4581,
+      "step": 39
+    },
+    {
+      "epoch": 0.07312614259597806,
+      "grad_norm": 0.33242480046792755,
+      "learning_rate": 2.9966760751036697e-05,
+      "loss": 0.4567,
+      "step": 40
+    },
+    {
+      "epoch": 0.07495429616087751,
+      "grad_norm": 0.3517734032444255,
+      "learning_rate": 2.9960445324864815e-05,
+      "loss": 0.4674,
+      "step": 41
+    },
+    {
+      "epoch": 0.07678244972577697,
+      "grad_norm": 0.3558065174543996,
+      "learning_rate": 2.995358173757765e-05,
+      "loss": 0.4718,
+      "step": 42
+    },
+    {
+      "epoch": 0.07861060329067641,
+      "grad_norm": 0.34290523065110684,
+      "learning_rate": 2.994617024066181e-05,
+      "loss": 0.4659,
+      "step": 43
+    },
+    {
+      "epoch": 0.08043875685557587,
+      "grad_norm": 0.3028572716833668,
+      "learning_rate": 2.9938211105679677e-05,
+      "loss": 0.4543,
+      "step": 44
+    },
+    {
+      "epoch": 0.08226691042047532,
+      "grad_norm": 0.36216688731700014,
+      "learning_rate": 2.9929704624259508e-05,
+      "loss": 0.4724,
+      "step": 45
+    },
+    {
+      "epoch": 0.08409506398537477,
+      "grad_norm": 0.34546125994172217,
+      "learning_rate": 2.992065110808469e-05,
+      "loss": 0.4717,
+      "step": 46
+    },
+    {
+      "epoch": 0.08592321755027423,
+      "grad_norm": 0.3173199655699041,
+      "learning_rate": 2.991105088888234e-05,
+      "loss": 0.4893,
+      "step": 47
+    },
+    {
+      "epoch": 0.08775137111517367,
+      "grad_norm": 0.27327168658587364,
+      "learning_rate": 2.990090431841117e-05,
+      "loss": 0.4877,
+      "step": 48
+    },
+    {
+      "epoch": 0.08957952468007313,
+      "grad_norm": 0.3207165383004196,
+      "learning_rate": 2.9890211768448572e-05,
+      "loss": 0.4666,
+      "step": 49
+    },
+    {
+      "epoch": 0.09140767824497258,
+      "grad_norm": 0.29795651824929764,
+      "learning_rate": 2.9878973630777012e-05,
+      "loss": 0.4764,
+      "step": 50
+    },
+    {
+      "epoch": 0.09323583180987204,
+      "grad_norm": 0.3066207186556079,
+      "learning_rate": 2.9867190317169665e-05,
+      "loss": 0.4793,
+      "step": 51
+    },
+    {
+      "epoch": 0.09506398537477148,
+      "grad_norm": 0.30152926589089146,
+      "learning_rate": 2.9854862259375326e-05,
+      "loss": 0.48,
+      "step": 52
+    },
+    {
+      "epoch": 0.09689213893967093,
+      "grad_norm": 0.31982845164198154,
+      "learning_rate": 2.9841989909102607e-05,
+      "loss": 0.4827,
+      "step": 53
+    },
+    {
+      "epoch": 0.09872029250457039,
+      "grad_norm": 0.3226249549846725,
+      "learning_rate": 2.982857373800337e-05,
+      "loss": 0.4815,
+      "step": 54
+    },
+    {
+      "epoch": 0.10054844606946983,
+      "grad_norm": 0.29313323454641665,
+      "learning_rate": 2.9814614237655445e-05,
+      "loss": 0.4624,
+      "step": 55
+    },
+    {
+      "epoch": 0.10237659963436929,
+      "grad_norm": 0.30450893112709426,
+      "learning_rate": 2.9800111919544632e-05,
+      "loss": 0.4856,
+      "step": 56
+    },
+    {
+      "epoch": 0.10420475319926874,
+      "grad_norm": 0.31077892246708605,
+      "learning_rate": 2.9785067315045943e-05,
+      "loss": 0.4801,
+      "step": 57
+    },
+    {
+      "epoch": 0.10603290676416818,
+      "grad_norm": 0.30352760576382176,
+      "learning_rate": 2.9769480975404143e-05,
+      "loss": 0.4462,
+      "step": 58
+    },
+    {
+      "epoch": 0.10786106032906764,
+      "grad_norm": 0.2820427097517702,
+      "learning_rate": 2.975335347171356e-05,
+      "loss": 0.4275,
+      "step": 59
+    },
+    {
+      "epoch": 0.10968921389396709,
+      "grad_norm": 0.3193688120609219,
+      "learning_rate": 2.9736685394897123e-05,
+      "loss": 0.4585,
+      "step": 60
+    },
+    {
+      "epoch": 0.11151736745886655,
+      "grad_norm": 0.29309453499656224,
+      "learning_rate": 2.9719477355684767e-05,
+      "loss": 0.4563,
+      "step": 61
+    },
+    {
+      "epoch": 0.113345521023766,
+      "grad_norm": 0.291897548964064,
+      "learning_rate": 2.9701729984591003e-05,
+      "loss": 0.4402,
+      "step": 62
+    },
+    {
+      "epoch": 0.11517367458866545,
+      "grad_norm": 0.3386425303422288,
+      "learning_rate": 2.9683443931891837e-05,
+      "loss": 0.4586,
+      "step": 63
+    },
+    {
+      "epoch": 0.1170018281535649,
+      "grad_norm": 0.28801030329886385,
+      "learning_rate": 2.966461986760096e-05,
+      "loss": 0.4452,
+      "step": 64
+    },
+    {
+      "epoch": 0.11882998171846434,
+      "grad_norm": 0.27225571075726074,
+      "learning_rate": 2.964525848144517e-05,
+      "loss": 0.4219,
+      "step": 65
+    },
+    {
+      "epoch": 0.1206581352833638,
+      "grad_norm": 0.3150014322578861,
+      "learning_rate": 2.9625360482839114e-05,
+      "loss": 0.4833,
+      "step": 66
+    },
+    {
+      "epoch": 0.12248628884826325,
+      "grad_norm": 0.28747617110884083,
+      "learning_rate": 2.9604926600859287e-05,
+      "loss": 0.4673,
+      "step": 67
+    },
+    {
+      "epoch": 0.12431444241316271,
+      "grad_norm": 0.2935455145106659,
+      "learning_rate": 2.958395758421733e-05,
+      "loss": 0.4492,
+      "step": 68
+    },
+    {
+      "epoch": 0.12614259597806216,
+      "grad_norm": 0.2748773662739781,
+      "learning_rate": 2.9562454201232583e-05,
+      "loss": 0.4763,
+      "step": 69
+    },
+    {
+      "epoch": 0.12797074954296161,
+      "grad_norm": 0.3040072222347735,
+      "learning_rate": 2.9540417239803954e-05,
+      "loss": 0.4658,
+      "step": 70
+    },
+    {
+      "epoch": 0.12979890310786105,
+      "grad_norm": 0.3401190893101851,
+      "learning_rate": 2.9517847507381022e-05,
+      "loss": 0.4619,
+      "step": 71
+    },
+    {
+      "epoch": 0.1316270566727605,
+      "grad_norm": 0.2832439537823879,
+      "learning_rate": 2.9494745830934473e-05,
+      "loss": 0.4594,
+      "step": 72
+    },
+    {
+      "epoch": 0.13345521023765997,
+      "grad_norm": 0.4216765622686639,
+      "learning_rate": 2.9471113056925786e-05,
+      "loss": 0.4939,
+      "step": 73
+    },
+    {
+      "epoch": 0.13528336380255943,
+      "grad_norm": 0.2884581020061622,
+      "learning_rate": 2.944695005127623e-05,
+      "loss": 0.458,
+      "step": 74
+    },
+    {
+      "epoch": 0.13711151736745886,
+      "grad_norm": 0.28039598694507106,
+      "learning_rate": 2.942225769933512e-05,
+      "loss": 0.4361,
+      "step": 75
+    },
+    {
+      "epoch": 0.13893967093235832,
+      "grad_norm": 0.27724633932247766,
+      "learning_rate": 2.939703690584741e-05,
+      "loss": 0.4557,
+      "step": 76
+    },
+    {
+      "epoch": 0.14076782449725778,
+      "grad_norm": 0.2694165757512015,
+      "learning_rate": 2.9371288594920484e-05,
+      "loss": 0.4332,
+      "step": 77
+    },
+    {
+      "epoch": 0.1425959780621572,
+      "grad_norm": 0.25780899472474833,
+      "learning_rate": 2.934501370999037e-05,
+      "loss": 0.4242,
+      "step": 78
+    },
+    {
+      "epoch": 0.14442413162705667,
+      "grad_norm": 0.2967403245642137,
+      "learning_rate": 2.93182132137871e-05,
+      "loss": 0.446,
+      "step": 79
+    },
+    {
+      "epoch": 0.14625228519195613,
+      "grad_norm": 0.34690556417034824,
+      "learning_rate": 2.9290888088299486e-05,
+      "loss": 0.4818,
+      "step": 80
+    },
+    {
+      "epoch": 0.1480804387568556,
+      "grad_norm": 0.3003683124367745,
+      "learning_rate": 2.9263039334739127e-05,
+      "loss": 0.462,
+      "step": 81
+    },
+    {
+      "epoch": 0.14990859232175502,
+      "grad_norm": 0.302108544256545,
+      "learning_rate": 2.92346679735037e-05,
+      "loss": 0.4561,
+      "step": 82
+    },
+    {
+      "epoch": 0.15173674588665448,
+      "grad_norm": 0.2841043066219529,
+      "learning_rate": 2.9205775044139608e-05,
+      "loss": 0.4684,
+      "step": 83
+    },
+    {
+      "epoch": 0.15356489945155394,
+      "grad_norm": 0.2952668737797339,
+      "learning_rate": 2.9176361605303867e-05,
+      "loss": 0.4693,
+      "step": 84
+    },
+    {
+      "epoch": 0.15539305301645337,
+      "grad_norm": 0.28847383193289927,
+      "learning_rate": 2.914642873472531e-05,
+      "loss": 0.452,
+      "step": 85
+    },
+    {
+      "epoch": 0.15722120658135283,
+      "grad_norm": 0.31050885319522226,
+      "learning_rate": 2.9115977529165132e-05,
+      "loss": 0.4621,
+      "step": 86
+    },
+    {
+      "epoch": 0.1590493601462523,
+      "grad_norm": 0.3143842313652269,
+      "learning_rate": 2.9085009104376663e-05,
+      "loss": 0.4563,
+      "step": 87
+    },
+    {
+      "epoch": 0.16087751371115175,
+      "grad_norm": 0.33281281256892775,
+      "learning_rate": 2.905352459506452e-05,
+      "loss": 0.437,
+      "step": 88
+    },
+    {
+      "epoch": 0.16270566727605118,
+      "grad_norm": 0.30726176715777354,
+      "learning_rate": 2.9021525154842998e-05,
+      "loss": 0.4614,
+      "step": 89
+    },
+    {
+      "epoch": 0.16453382084095064,
+      "grad_norm": 0.31519069611911227,
+      "learning_rate": 2.8989011956193834e-05,
+      "loss": 0.4584,
+      "step": 90
+    },
+    {
+      "epoch": 0.1663619744058501,
+      "grad_norm": 0.3142796251849267,
+      "learning_rate": 2.8955986190423225e-05,
+      "loss": 0.4848,
+      "step": 91
+    },
+    {
+      "epoch": 0.16819012797074953,
+      "grad_norm": 0.2831585707772231,
+      "learning_rate": 2.892244906761819e-05,
+      "loss": 0.4463,
+      "step": 92
+    },
+    {
+      "epoch": 0.170018281535649,
+      "grad_norm": 0.3271624604307319,
+      "learning_rate": 2.8888401816602207e-05,
+      "loss": 0.4496,
+      "step": 93
+    },
+    {
+      "epoch": 0.17184643510054845,
+      "grad_norm": 0.3265076622565222,
+      "learning_rate": 2.885384568489023e-05,
+      "loss": 0.434,
+      "step": 94
+    },
+    {
+      "epoch": 0.1736745886654479,
+      "grad_norm": 0.3384143662294581,
+      "learning_rate": 2.881878193864294e-05,
+      "loss": 0.4662,
+      "step": 95
+    },
+    {
+      "epoch": 0.17550274223034734,
+      "grad_norm": 0.29519544921435537,
+      "learning_rate": 2.878321186262037e-05,
+      "loss": 0.4415,
+      "step": 96
+    },
+    {
+      "epoch": 0.1773308957952468,
+      "grad_norm": 0.3152573413188835,
+      "learning_rate": 2.8747136760134827e-05,
+      "loss": 0.4525,
+      "step": 97
+    },
+    {
+      "epoch": 0.17915904936014626,
+      "grad_norm": 0.2911315525075031,
+      "learning_rate": 2.871055795300315e-05,
+      "loss": 0.4393,
+      "step": 98
+    },
+    {
+      "epoch": 0.1809872029250457,
+      "grad_norm": 0.28890139736154113,
+      "learning_rate": 2.8673476781498242e-05,
+      "loss": 0.4301,
+      "step": 99
+    },
+    {
+      "epoch": 0.18281535648994515,
+      "grad_norm": 0.29566233008031895,
+      "learning_rate": 2.8635894604300018e-05,
+      "loss": 0.4477,
+      "step": 100
+    },
+    {
+      "epoch": 0.1846435100548446,
+      "grad_norm": 0.2759848384654238,
+      "learning_rate": 2.859781279844556e-05,
+      "loss": 0.4477,
+      "step": 101
+    },
+    {
+      "epoch": 0.18647166361974407,
+      "grad_norm": 0.3231166719493857,
+      "learning_rate": 2.855923275927871e-05,
+      "loss": 0.4732,
+      "step": 102
+    },
+    {
+      "epoch": 0.1882998171846435,
+      "grad_norm": 0.27671665616727253,
+      "learning_rate": 2.8520155900398922e-05,
+      "loss": 0.4348,
+      "step": 103
+    },
+    {
+      "epoch": 0.19012797074954296,
+      "grad_norm": 0.3373290606091851,
+      "learning_rate": 2.8480583653609457e-05,
+      "loss": 0.4772,
+      "step": 104
+    },
+    {
+      "epoch": 0.19195612431444242,
+      "grad_norm": 0.270804966443481,
+      "learning_rate": 2.844051746886495e-05,
+      "loss": 0.4522,
+      "step": 105
+    },
+    {
+      "epoch": 0.19378427787934185,
+      "grad_norm": 0.28232177001780473,
+      "learning_rate": 2.8399958814218258e-05,
+      "loss": 0.465,
+      "step": 106
+    },
+    {
+      "epoch": 0.1956124314442413,
+      "grad_norm": 0.32735140894867865,
+      "learning_rate": 2.8358909175766674e-05,
+      "loss": 0.4665,
+      "step": 107
+    },
+    {
+      "epoch": 0.19744058500914077,
+      "grad_norm": 0.3535841008181332,
+      "learning_rate": 2.831737005759749e-05,
+      "loss": 0.4817,
+      "step": 108
+    },
+    {
+      "epoch": 0.19926873857404023,
+      "grad_norm": 0.31153302714419157,
+      "learning_rate": 2.8275342981732868e-05,
+      "loss": 0.4774,
+      "step": 109
+    },
+    {
+      "epoch": 0.20109689213893966,
+      "grad_norm": 0.3414165680532852,
+      "learning_rate": 2.8232829488074077e-05,
+      "loss": 0.4354,
+      "step": 110
+    },
+    {
+      "epoch": 0.20292504570383912,
+      "grad_norm": 0.2657136503074252,
+      "learning_rate": 2.8189831134345074e-05,
+      "loss": 0.4403,
+      "step": 111
+    },
+    {
+      "epoch": 0.20475319926873858,
+      "grad_norm": 0.2963856605986798,
+      "learning_rate": 2.8146349496035426e-05,
+      "loss": 0.4262,
+      "step": 112
+    },
+    {
+      "epoch": 0.20658135283363802,
+      "grad_norm": 0.3119283296440065,
+      "learning_rate": 2.8102386166342582e-05,
+      "loss": 0.4418,
+      "step": 113
+    },
+    {
+      "epoch": 0.20840950639853748,
+      "grad_norm": 0.37109957781553604,
+      "learning_rate": 2.8057942756113504e-05,
+      "loss": 0.4765,
+      "step": 114
+    },
+    {
+      "epoch": 0.21023765996343693,
+      "grad_norm": 0.2999662023442714,
+      "learning_rate": 2.8013020893785635e-05,
+      "loss": 0.4539,
+      "step": 115
+    },
+    {
+      "epoch": 0.21206581352833637,
+      "grad_norm": 0.28970493967104405,
+      "learning_rate": 2.796762222532723e-05,
+      "loss": 0.4289,
+      "step": 116
+    },
+    {
+      "epoch": 0.21389396709323583,
+      "grad_norm": 0.2939203180452282,
+      "learning_rate": 2.7921748414177063e-05,
+      "loss": 0.4689,
+      "step": 117
+    },
+    {
+      "epoch": 0.21572212065813529,
+      "grad_norm": 0.3201929927655123,
+      "learning_rate": 2.787540114118345e-05,
+      "loss": 0.4338,
+      "step": 118
+    },
+    {
+      "epoch": 0.21755027422303475,
+      "grad_norm": 0.2864175962342283,
+      "learning_rate": 2.7828582104542694e-05,
+      "loss": 0.4464,
+      "step": 119
+    },
+    {
+      "epoch": 0.21937842778793418,
+      "grad_norm": 0.28592410203121005,
+      "learning_rate": 2.7781293019736845e-05,
+      "loss": 0.4397,
+      "step": 120
+    },
+    {
+      "epoch": 0.22120658135283364,
+      "grad_norm": 0.3304180569852307,
+      "learning_rate": 2.7733535619470835e-05,
+      "loss": 0.4481,
+      "step": 121
+    },
+    {
+      "epoch": 0.2230347349177331,
+      "grad_norm": 0.3390393526626585,
+      "learning_rate": 2.7685311653609004e-05,
+      "loss": 0.4432,
+      "step": 122
+    },
+    {
+      "epoch": 0.22486288848263253,
+      "grad_norm": 0.2940159306891994,
+      "learning_rate": 2.7636622889110975e-05,
+      "loss": 0.475,
+      "step": 123
+    },
+    {
+      "epoch": 0.226691042047532,
+      "grad_norm": 0.31229638977483115,
+      "learning_rate": 2.758747110996693e-05,
+      "loss": 0.4643,
+      "step": 124
+    },
+    {
+      "epoch": 0.22851919561243145,
+      "grad_norm": 0.285967777532962,
+      "learning_rate": 2.7537858117132217e-05,
+      "loss": 0.4505,
+      "step": 125
+    },
+    {
+      "epoch": 0.2303473491773309,
+      "grad_norm": 0.3096207093074659,
+      "learning_rate": 2.7487785728461383e-05,
+      "loss": 0.4606,
+      "step": 126
+    },
+    {
+      "epoch": 0.23217550274223034,
+      "grad_norm": 0.3196007759195916,
+      "learning_rate": 2.7437255778641548e-05,
+      "loss": 0.4688,
+      "step": 127
+    },
+    {
+      "epoch": 0.2340036563071298,
+      "grad_norm": 0.278093004843679,
+      "learning_rate": 2.7386270119125193e-05,
+      "loss": 0.4476,
+      "step": 128
+    },
+    {
+      "epoch": 0.23583180987202926,
+      "grad_norm": 0.28238850493053447,
+      "learning_rate": 2.7334830618062327e-05,
+      "loss": 0.4328,
+      "step": 129
+    },
+    {
+      "epoch": 0.2376599634369287,
+      "grad_norm": 0.31893781223089274,
+      "learning_rate": 2.728293916023202e-05,
+      "loss": 0.4368,
+      "step": 130
+    },
+    {
+      "epoch": 0.23948811700182815,
+      "grad_norm": 0.3226432084535994,
+      "learning_rate": 2.7230597646973355e-05,
+      "loss": 0.4693,
+      "step": 131
+    },
+    {
+      "epoch": 0.2413162705667276,
+      "grad_norm": 0.3098641582546802,
+      "learning_rate": 2.717780799611576e-05,
+      "loss": 0.4677,
+      "step": 132
+    },
+    {
+      "epoch": 0.24314442413162707,
+      "grad_norm": 0.316005877064317,
+      "learning_rate": 2.7124572141908737e-05,
+      "loss": 0.4641,
+      "step": 133
+    },
+    {
+      "epoch": 0.2449725776965265,
+      "grad_norm": 0.29116768124986503,
+      "learning_rate": 2.707089203495098e-05,
+      "loss": 0.4504,
+      "step": 134
+    },
+    {
+      "epoch": 0.24680073126142596,
+      "grad_norm": 0.3312565101776482,
+      "learning_rate": 2.701676964211893e-05,
+      "loss": 0.4869,
+      "step": 135
+    },
+    {
+      "epoch": 0.24862888482632542,
+      "grad_norm": 0.3307114085092842,
+      "learning_rate": 2.696220694649467e-05,
+      "loss": 0.4307,
+      "step": 136
+    },
+    {
+      "epoch": 0.25045703839122485,
+      "grad_norm": 0.3139451066311321,
+      "learning_rate": 2.69072059472933e-05,
+      "loss": 0.4593,
+      "step": 137
+    },
+    {
+      "epoch": 0.2522851919561243,
+      "grad_norm": 0.3298447274769771,
+      "learning_rate": 2.685176865978965e-05,
+      "loss": 0.4544,
+      "step": 138
+    },
+    {
+      "epoch": 0.25411334552102377,
+      "grad_norm": 0.3032493627313141,
+      "learning_rate": 2.6795897115244478e-05,
+      "loss": 0.4279,
+      "step": 139
+    },
+    {
+      "epoch": 0.25594149908592323,
+      "grad_norm": 0.2658733658787214,
+      "learning_rate": 2.6739593360830006e-05,
+      "loss": 0.4106,
+      "step": 140
+    },
+    {
+      "epoch": 0.2577696526508227,
+      "grad_norm": 0.3190884630430669,
+      "learning_rate": 2.668285945955493e-05,
+      "loss": 0.4662,
+      "step": 141
+    },
+    {
+      "epoch": 0.2595978062157221,
+      "grad_norm": 0.34411371393720197,
+      "learning_rate": 2.6625697490188832e-05,
+      "loss": 0.4499,
+      "step": 142
+    },
+    {
+      "epoch": 0.26142595978062155,
+      "grad_norm": 0.32823365391601855,
+      "learning_rate": 2.6568109547185996e-05,
+      "loss": 0.4783,
+      "step": 143
+    },
+    {
+      "epoch": 0.263254113345521,
+      "grad_norm": 0.30268317080382134,
+      "learning_rate": 2.651009774060868e-05,
+      "loss": 0.4677,
+      "step": 144
+    },
+    {
+      "epoch": 0.26508226691042047,
+      "grad_norm": 0.290999041829207,
+      "learning_rate": 2.6451664196049802e-05,
+      "loss": 0.4461,
+      "step": 145
+    },
+    {
+      "epoch": 0.26691042047531993,
+      "grad_norm": 0.3169422559498593,
+      "learning_rate": 2.639281105455505e-05,
+      "loss": 0.4503,
+      "step": 146
+    },
+    {
+      "epoch": 0.2687385740402194,
+      "grad_norm": 0.3189364221479283,
+      "learning_rate": 2.6333540472544442e-05,
+      "loss": 0.4335,
+      "step": 147
+    },
+    {
+      "epoch": 0.27056672760511885,
+      "grad_norm": 0.30758294437768796,
+      "learning_rate": 2.6273854621733286e-05,
+      "loss": 0.4504,
+      "step": 148
+    },
+    {
+      "epoch": 0.27239488117001825,
+      "grad_norm": 0.2849217195325153,
+      "learning_rate": 2.621375568905266e-05,
+      "loss": 0.4487,
+      "step": 149
+    },
+    {
+      "epoch": 0.2742230347349177,
+      "grad_norm": 0.344396845889534,
+      "learning_rate": 2.615324587656921e-05,
+      "loss": 0.4821,
+      "step": 150
+    },
+    {
+      "epoch": 0.2760511882998172,
+      "grad_norm": 0.2696584787135129,
+      "learning_rate": 2.6092327401404538e-05,
+      "loss": 0.475,
+      "step": 151
+    },
+    {
+      "epoch": 0.27787934186471663,
+      "grad_norm": 0.30241018017889437,
+      "learning_rate": 2.6031002495653913e-05,
+      "loss": 0.4342,
+      "step": 152
+    },
+    {
+      "epoch": 0.2797074954296161,
+      "grad_norm": 0.28693150625713587,
+      "learning_rate": 2.596927340630451e-05,
+      "loss": 0.4359,
+      "step": 153
+    },
+    {
+      "epoch": 0.28153564899451555,
+      "grad_norm": 0.29754809227022666,
+      "learning_rate": 2.590714239515306e-05,
+      "loss": 0.4438,
+      "step": 154
+    },
+    {
+      "epoch": 0.283363802559415,
+      "grad_norm": 0.299567522325594,
+      "learning_rate": 2.584461173872301e-05,
+      "loss": 0.4532,
+      "step": 155
+    },
+    {
+      "epoch": 0.2851919561243144,
+      "grad_norm": 0.2813266176963191,
+      "learning_rate": 2.5781683728181066e-05,
+      "loss": 0.4405,
+      "step": 156
+    },
+    {
+      "epoch": 0.2870201096892139,
+      "grad_norm": 0.3171717930616808,
+      "learning_rate": 2.5718360669253276e-05,
+      "loss": 0.454,
+      "step": 157
+    },
+    {
+      "epoch": 0.28884826325411334,
+      "grad_norm": 0.30159353684035844,
+      "learning_rate": 2.565464488214053e-05,
+      "loss": 0.4375,
+      "step": 158
+    },
+    {
+      "epoch": 0.2906764168190128,
+      "grad_norm": 0.2692705044539712,
+      "learning_rate": 2.559053870143356e-05,
+      "loss": 0.4276,
+      "step": 159
+    },
+    {
+      "epoch": 0.29250457038391225,
+      "grad_norm": 0.30691595589677334,
+      "learning_rate": 2.5526044476027383e-05,
+      "loss": 0.4606,
+      "step": 160
+    },
+    {
+      "epoch": 0.2943327239488117,
+      "grad_norm": 0.31630931258544637,
+      "learning_rate": 2.5461164569035244e-05,
+      "loss": 0.4406,
+      "step": 161
+    },
+    {
+      "epoch": 0.2961608775137112,
+      "grad_norm": 0.2440944204924941,
+      "learning_rate": 2.5395901357702032e-05,
+      "loss": 0.4511,
+      "step": 162
+    },
+    {
+      "epoch": 0.2979890310786106,
+      "grad_norm": 0.31355225894665767,
+      "learning_rate": 2.533025723331718e-05,
+      "loss": 0.4384,
+      "step": 163
+    },
+    {
+      "epoch": 0.29981718464351004,
+      "grad_norm": 0.2828232991554723,
+      "learning_rate": 2.526423460112703e-05,
+      "loss": 0.4318,
+      "step": 164
+    },
+    {
+      "epoch": 0.3016453382084095,
+      "grad_norm": 0.2872196769388632,
+      "learning_rate": 2.5197835880246702e-05,
+      "loss": 0.4508,
+      "step": 165
+    },
+    {
+      "epoch": 0.30347349177330896,
+      "grad_norm": 0.27755470022103107,
+      "learning_rate": 2.51310635035715e-05,
+      "loss": 0.4443,
+      "step": 166
+    },
+    {
+      "epoch": 0.3053016453382084,
+      "grad_norm": 0.29288725811791394,
+      "learning_rate": 2.506391991768771e-05,
+      "loss": 0.4437,
+      "step": 167
+    },
+    {
+      "epoch": 0.3071297989031079,
+      "grad_norm": 0.28756847297478805,
+      "learning_rate": 2.4996407582782987e-05,
+      "loss": 0.4306,
+      "step": 168
+    },
+    {
+      "epoch": 0.30895795246800734,
+      "grad_norm": 0.3062510638432968,
+      "learning_rate": 2.4928528972556207e-05,
+      "loss": 0.4401,
+      "step": 169
+    },
+    {
+      "epoch": 0.31078610603290674,
+      "grad_norm": 0.28844799158530887,
+      "learning_rate": 2.486028657412683e-05,
+      "loss": 0.465,
+      "step": 170
+    },
+    {
+      "epoch": 0.3126142595978062,
+      "grad_norm": 0.30254982711927847,
+      "learning_rate": 2.479168288794377e-05,
+      "loss": 0.4257,
+      "step": 171
+    },
+    {
+      "epoch": 0.31444241316270566,
+      "grad_norm": 0.29617551569459377,
+      "learning_rate": 2.472272042769377e-05,
+      "loss": 0.4413,
+      "step": 172
+    },
+    {
+      "epoch": 0.3162705667276051,
+      "grad_norm": 0.2894388824454487,
+      "learning_rate": 2.4653401720209316e-05,
+      "loss": 0.4339,
+      "step": 173
+    },
+    {
+      "epoch": 0.3180987202925046,
+      "grad_norm": 0.31278541819511707,
+      "learning_rate": 2.4583729305376014e-05,
+      "loss": 0.4433,
+      "step": 174
+    },
+    {
+      "epoch": 0.31992687385740404,
+      "grad_norm": 0.29889716089103313,
+      "learning_rate": 2.451370573603959e-05,
+      "loss": 0.4465,
+      "step": 175
+    },
+    {
+      "epoch": 0.3217550274223035,
+      "grad_norm": 0.30650603689771794,
+      "learning_rate": 2.4443333577912285e-05,
+      "loss": 0.4497,
+      "step": 176
+    },
+    {
+      "epoch": 0.3235831809872029,
+      "grad_norm": 0.27739674261767966,
+      "learning_rate": 2.437261540947889e-05,
+      "loss": 0.4417,
+      "step": 177
+    },
+    {
+      "epoch": 0.32541133455210236,
+      "grad_norm": 0.29186196118144964,
+      "learning_rate": 2.430155382190225e-05,
+      "loss": 0.46,
+      "step": 178
+    },
+    {
+      "epoch": 0.3272394881170018,
+      "grad_norm": 0.28342780349608687,
+      "learning_rate": 2.4230151418928326e-05,
+      "loss": 0.4414,
+      "step": 179
+    },
+    {
+      "epoch": 0.3290676416819013,
+      "grad_norm": 0.2751850949398033,
+      "learning_rate": 2.415841081679079e-05,
+      "loss": 0.4569,
+      "step": 180
+    },
+    {
+      "epoch": 0.33089579524680074,
+      "grad_norm": 0.2848165003785897,
+      "learning_rate": 2.4086334644115176e-05,
+      "loss": 0.4167,
+      "step": 181
+    },
+    {
+      "epoch": 0.3327239488117002,
+      "grad_norm": 0.26869428432353776,
+      "learning_rate": 2.4013925541822543e-05,
+      "loss": 0.4393,
+      "step": 182
+    },
+    {
+      "epoch": 0.33455210237659966,
+      "grad_norm": 0.3041074292613331,
+      "learning_rate": 2.3941186163032736e-05,
+      "loss": 0.443,
+      "step": 183
+    },
+    {
+      "epoch": 0.33638025594149906,
+      "grad_norm": 0.3054719627730434,
+      "learning_rate": 2.3868119172967145e-05,
+      "loss": 0.4711,
+      "step": 184
+    },
+    {
+      "epoch": 0.3382084095063985,
+      "grad_norm": 0.294864775838586,
+      "learning_rate": 2.379472724885108e-05,
+      "loss": 0.4208,
+      "step": 185
+    },
+    {
+      "epoch": 0.340036563071298,
+      "grad_norm": 0.2815964015764938,
+      "learning_rate": 2.3721013079815645e-05,
+      "loss": 0.445,
+      "step": 186
+    },
+    {
+      "epoch": 0.34186471663619744,
+      "grad_norm": 0.31854040107909304,
+      "learning_rate": 2.3646979366799234e-05,
+      "loss": 0.4601,
+      "step": 187
+    },
+    {
+      "epoch": 0.3436928702010969,
+      "grad_norm": 0.28167691281400475,
+      "learning_rate": 2.3572628822448546e-05,
+      "loss": 0.4506,
+      "step": 188
+    },
+    {
+      "epoch": 0.34552102376599636,
+      "grad_norm": 0.2771446663943378,
+      "learning_rate": 2.3497964171019214e-05,
+      "loss": 0.4358,
+      "step": 189
+    },
+    {
+      "epoch": 0.3473491773308958,
+      "grad_norm": 0.27745556919254083,
+      "learning_rate": 2.3422988148275963e-05,
+      "loss": 0.4461,
+      "step": 190
+    },
+    {
+      "epoch": 0.3491773308957952,
+      "grad_norm": 0.26029043603341223,
+      "learning_rate": 2.3347703501392373e-05,
+      "loss": 0.4538,
+      "step": 191
+    },
+    {
+      "epoch": 0.3510054844606947,
+      "grad_norm": 0.2744751742780149,
+      "learning_rate": 2.3272112988850237e-05,
+      "loss": 0.4343,
+      "step": 192
+    },
+    {
+      "epoch": 0.35283363802559414,
+      "grad_norm": 0.3148709000115808,
+      "learning_rate": 2.319621938033848e-05,
+      "loss": 0.4421,
+      "step": 193
+    },
+    {
+      "epoch": 0.3546617915904936,
+      "grad_norm": 0.2802326000313149,
+      "learning_rate": 2.3120025456651658e-05,
+      "loss": 0.4528,
+      "step": 194
+    },
+    {
+      "epoch": 0.35648994515539306,
+      "grad_norm": 0.25928215844810953,
+      "learning_rate": 2.3043534009588108e-05,
+      "loss": 0.4405,
+      "step": 195
+    },
+    {
+      "epoch": 0.3583180987202925,
+      "grad_norm": 0.2732416188380195,
+      "learning_rate": 2.296674784184761e-05,
+      "loss": 0.4123,
+      "step": 196
+    },
+    {
+      "epoch": 0.360146252285192,
+      "grad_norm": 0.2616002327630866,
+      "learning_rate": 2.288966976692873e-05,
+      "loss": 0.4211,
+      "step": 197
+    },
+    {
+      "epoch": 0.3619744058500914,
+      "grad_norm": 0.25552504229923495,
+      "learning_rate": 2.2812302609025692e-05,
+      "loss": 0.4219,
+      "step": 198
+    },
+    {
+      "epoch": 0.36380255941499084,
+      "grad_norm": 0.26460690701785383,
+      "learning_rate": 2.2734649202924955e-05,
+      "loss": 0.4519,
+      "step": 199
+    },
+    {
+      "epoch": 0.3656307129798903,
+      "grad_norm": 0.2703925981362186,
+      "learning_rate": 2.265671239390128e-05,
+      "loss": 0.4525,
+      "step": 200
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 547,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 200,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 131774435229696.0,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:72b384d7a9d80345499cef72b6c2d7fe55afcb40039d8f42c6f7fdcd9787a50c
+size 8081